Distribution Estimation to Automate Transformation Policies for Self-Supervision
arXiv:2111.12265
Abstract
In recent visual self-supervision works, an imitated classification objective, called pretext task, is established by assigning labels to transformed or augmented input images. The goal of pretext can be predicting what transformations are applied to the image. However, it is observed that image transformations already present in the dataset might be less effective in learning such self-supervised representations. Building on this observation, we propose a framework based on generative adversarial network to automatically find the transformations which are not present in the input dataset and thus effective for the self-supervised learning. This automated policy allows to estimate the transformation distribution of a dataset and also construct its complementary distribution from which training pairs are sampled for the pretext task. We evaluated our framework using several visual recognition datasets to show the efficacy of our automated transformation policy.
NeurIPS 2021 Workshop: Self-Supervised Learning - Theory and Practice
References in corpus (4)
- Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
- Skin Lesion Analysis Toward Melanoma Detection 2018: A Challenge Hosted by the International Skin Imaging Collaboration (ISIC)
- Exploiting Unlabeled Data in CNNs by Self-supervised Learning to Rank
- Towards a Hypothesis on Visual Transformation based Self-Supervision